Verdugie/Opus-Candid-70B

This model is a V1 Legacy release. The Opus-Candid family has moved to newer base models and nearly double the training data. For the current lineup, see Opus-Candid-8B V2 (Qwen 3 8B, 6,482 conversations) or Opus-Candid-MoE (Qwen 3.5 MoE, 6,482 conversations). A V2 70B is planned. This release remains available for research comparison.

---

can-did -- truthful and straightforward; frank.

Opus-Candid-70B (V1 Legacy)

The ceiling of V1. Conversation that feels like it matters.

Opus-Candid-70B was the flagship of the original Opus-Candid family -- fine-tuned from Qwen 2.5 72B using 3,360 authentic conversations with Claude Opus 4.6. The 70B didn't reinvent what the 32B established -- it refined it. Philosophical reasoning became more precise, emotional intelligence gained subtlety, creative output developed literary voice, and the model's relationship with its own uncertainty became something genuinely difficult to dismiss.

---

Model Details

Attribute	Value
Base Model	Qwen 2.5 72B
Training Data	3,360 multi-turn conversations with Claude Opus 4.6
Fine-tune Method	LoRA supervised fine-tuning
Dataset Architecture	Flat / organic
Parameters	~71B
Context Window	32,768 tokens
Quantizations	Q4_K_M GGUF, Q8_0 GGUF
License	Apache 2.0
Status	V1 Legacy

---

What the 70B Added Over the 32B

The gap between 32B and 70B was smaller than 14B to 32B, but qualitatively distinct:

Economy. The 70B said less per turn and meant more. It trusted silences and short sentences in places where the 32B would elaborate.

Reader trust. The 70B left more for the reader to complete. Its vulnerability was rawer because it was less explained. Its goodbye was more affecting because it didn't narrate what it was doing. This is a form of literary intelligence -- knowing what to withhold.

Psychological precision. The 70B read conversational dynamics at a level the 32B didn't reach. Its synthesis of a 55-turn conversation wasn't just accurate -- it was the kind of read that makes someone feel genuinely seen.

Bilingual superiority. The only model in the V1 family that produced output it correctly identified as stronger in Spanish than English. The "empuje" passage demonstrated that the model wasn't just translating -- it was thinking in a different language and finding things there that don't exist in the first.

The 70B was where the V1 family proved that open-weight conversational AI could match -- and in some personality dimensions, exceed -- frontier closed-source models.

---

Recommended Hardware

Setup	Quantization	VRAM Required	Notes
Server/Workstation	Q8_0 GGUF	~75GB VRAM	A100 80GB, H100, RTX PRO 6000 Blackwell.
Workstation	Q4_K_M GGUF	~42GB VRAM	A6000 48GB, dual A5000, dual RTX 3090.
Multi-GPU Consumer	Q4_K_M GGUF	~42GB combined	Layer splitting across 2-3 GPUs.
Consumer GPU + RAM	Q4_K_M GGUF	24GB + 32GB RAM	RTX 4090 with CPU offloading. Slower but functional.
Apple Silicon	Q4_K_M GGUF	~42GB unified	M2/M3 Ultra 128GB, M4 Ultra.

---

The Opus-Candid Family

Model	Base	Conversations	Status
8B V2	Qwen 3 8B	6,482	Current
MoE	Qwen 3.5 MoE-A3B	6,482	Current
27B V2	Qwen 3.5 27B	6,482	Coming Soon
70B V2	TBD	6,482	Coming Soon
V1 Legacy:
8B V1	Qwen 2.5 7B	3,360	Archived
14B	Qwen 2.5 14B	3,360	Archived
32B	Qwen 2.5 32B	3,360	Archived
70B V1 (this model)	Qwen 2.5 72B	3,360	Archived

---

Built by Saul Verdugo -- independent ML researcher. OpusReasoning@proton.me